Enterprise AI for Process Optimization

Project Challenge

A leading fertilizer company wants to decrease its energy costs and carbon footprint by optimizing the allocation of the steam generated from the sulfuric acid production process. The company built cogeneration plants as part of its fertilizer process facilities to use the heat released by the sulfuric acid oxidation; this concurrently generates the steam needed for fertilizer production and electricity for plant operations.

The plants process sulfur into sulfuric acid, releasing heat which is converted into steam. Each process facility has a cogeneration plant with multiple steam turbogenerators (TG) operated by TG chief operators. The operators are responsible for distributing high-pressure steam from sulfuric acid oxidation across TGs and extracting medium and low-pressure steam needed to concentrate the phosphoric acid at phosphoric acid plants. TG chief can also use let-down (LD) valves to by-pass the TGs and send the steam directly to the phosphoric acid plant. While the fertilizer steam demand can be met with the bypass method, no electricity is generated, decreasing cogeneration performance. TG chief operators were responsible for meeting steam demand from phosphoric plants while reducing the company’s energy spend and carbon footprint, but the results have been below expectations.

The company attempted to improve cogeneration performance by providing additional training and tools to the TG chief operators, but the performance continued to be sub-optimal.

About the Company

  • $9 billion annual revenue in 2020
  • 35M tons of fertilizer production capacity
  • Operations in 9 different countries
  • 13,000 employees

Project Highlights

  • 12 weeks from kickoff to pre-production application
  • Integrated two years of historical data, comprising of nearly 200 tags at
    5-minute intervals per data point
  • Created unified data image from 80+ different P&IDs
  • Implemented more than 25 equations as problem optimization constraints
  • Trained six different ML models to predict power generated by turbogenerators
  • Configured the BHC3 Process Optimization application user interface to include gamification elements

Approach

Over 12 weeks, the BHC3 team configured BHC3 Process Optimization for the biggest and most complex process facilities of the global fertilizer. The team reviewed more than 80 different P&ID diagrams and mapped out all the relevant tags for the high, medium, and low-pressure steam headers. The team then integrated 2 years of historical sensor data from 1,000 tags into the BHC3 AI Suite, creating a unified data image for the entire steam balance system.

The BHC3 team used the ML models to solve the power optimization problem at the facility level. The final function has 6 optimization variables and more than 25 optimization constraint equations. Under a steady-state assumption, BHC3 Process Optimization recommends inlet steam and extraction flows that

Results

$7.2M
Potential annual energy saving when deployed across all plants
15%
Increase in energy production on average
70%+
Of recommendations increased energy output
68,000 tons
Of carbon dioxide equivalent emissions saved in 1 year when deployed across all plants

Solution Architecture

BHC3 Process Optimization

Proven results in weeks, not years

timeline
Get insights into BHC3 capabilities, enterprise AI best practices and highest-value use cases.
Understand BHC3™ AI Suite's capabilities, its model-driven architecture and test it against your company's sample data set.
Identify a high-impact business problem and collaborate with the BHC3 team to rapidly build an AI application that solves it.
Scale and deploy a tested BHC3 application into production. Incorporate user feedback and optimize algorithms to drive maximum economic value.

Thank you for your interest in BHC3.ai

We'll review your information and a team member will get back to you within 24-48 hours.

Return to home
Loading form...